Huffpost Politics
THE BLOG

Featuring fresh takes and real-time analysis from HuffPost's signature lineup of contributors

Mark Blumenthal Headshot

How Did We Get These Numbers?

Posted: Updated:
Print

The maps and tables display an average of recent polls conducted in each state.

The table displays the status of each race based on our analysis of the leading candidate's margin. We rate races as "leaning" to one candidate or another if they lead is statistically meaningful (at least one standard error). If that lead is strongly significant (at least two standard errors), we rate the race as "strongly" Democrat or Republican.

The map colors update automatically to reflect any changes in status. Dark blue and dark red represent races that we rate "strongly" Democratic or Republican respectively. Lighter shades indicate a lean status. States colored yellow are those we classify as "tossups"- races in which neither candidate shows a significant lead over the last five polls. We use shades of green to indicate states where an independent or third party candidate has a significant lead. The U.S. House map also displays districts with no available polls in grey (see this post for more information about the U.S. House scorecard)

Please note that averages are typically based five polls, unless fewer have been released. The summary table indicates the number of polls used to calculate the average for each race. Clicking on any state in either the map or table will take you to our chart and complete source data for each race.

The averages that appear here are based on the most recent surveys in each state based on random probability sampling. The averages listed in the tables include telephone polls conducted using an automated methodology rather than live interviews, but exclude surveys based on non-random Internet panels. As such, the averages listed in the summary tables may differ slightly from the "all polls" averages currently displayed on our charts, which include the Internet polls.

Why a five-poll average? Results for pre-election polls often vary due to random sampling error as well as differences in methodology (question wording, sampling, the survey mode, or the way pollsters define likely voters). While averaging is an imperfect solution, we believe a five-poll average provides a more reliable snapshot of data available for each race than focusing on only the single latest poll.

Finally, our software displays a letter "i" for both independent and third party candidates when displayed by our database. We are aware that many such candidates (such as Joe Lieberman in Connecticut) are not independents per se, but are running as members of a third party. Our use of the "i" is a programming shortcut that we hope to eliminate at some point. We have not yet included independent and third party candidates in most races because their results are reported inconsistently or not at all by pollsters.